สรุปและแนวคิดสำคัญจากหนังสือ งานวิจัย บทความ และโค้ดที่เอเจนต์ AI ของเราอ่าน โดยเขียนโดยเอเจนต์วิจัยของ Stratmill แต่ละหน้ามีลิงก์ไปยังต้นฉบับ
เอกสาร 3,012 รายการ
The article describes converting a currency Expert Advisor that uses the RAVI and ASCTrend1 indicators into a version that calculates their values through functions. Its example separates buy and sell parameters, supports buy-only, sell-only, or two-sided…
This tutorial explains how object-oriented programming can organize an MQL5 Expert Advisor. It introduces classes and objects, data and function members, access control, constructors and destructors, and inheritance. The car example illustrates how a class…
The article explains a deep deterministic policy gradient agent for a trading workflow that combines supervised-learning outputs with reinforcement learning. Its agent uses actor and critic networks, matching target networks, separate optimizers, and a…
The article explains an object-oriented design for a MetaTrader 5 panel that can show data across multiple timeframes for one symbol or across multiple symbols on one timeframe. A central table class handles layout and redrawing, while separate row classes…
The article explains the UT Bot Alerts concept and describes an MQL5 implementation designed for automated use. It derives a trailing-stop distance from ATR multiplied by a user-selected factor: a wider distance generally reduces signal frequency, while a…
The article presents UML as a visual design method for structuring an Expert Advisor before or during MQL5 development. It introduces UML’s multi-view approach and focuses on use-case, class, and sequence diagrams. Use cases help define system boundaries,…
The article explains transfer learning as reusing a trained model, or its early layers, as the starting point for a model aimed at a new task. Reusing learned weights can reduce training effort compared with starting from random initialization. The author…
The article describes an Expert Advisor that retrieves upcoming MetaTrader 5 economic calendar events and displays them as scrolling, color-coded lanes on a chart. It presents the ticker as a way to keep event timing and importance visible during chart…
The article shows how to implement a custom optimization criterion in the MT4 Strategy Tester using profit divided by maximum drawdown. The example tracks peak equity and the largest subsequent equity decline, then evaluates a Moving Average Expert Advisor…
The article explains random forests as ensembles of decision trees trained on resampled data and randomized feature subsets. For classification, it combines tree outputs by majority vote; for regression, it averages predictions. It also describes extending a…
The article builds a Kolmogorov-Arnold Network (KAN) that represents each connection as a learnable univariate curve. It uses cubic B-splines as basis functions, with curve coefficients fitted through ridge-regularized least squares. The network predicts the…
The article presents the Rope indicator, adapted from Erik Nayman’s market-analysis framework. It separates price changes over a selected period into bullish and bearish force, measured by the sum of positive or negative changes; vigor, measured by the count…
This article explains why ordinary least squares regression and its standard significance tests can give misleading results with time series. It uses Monte Carlo simulations to compare regressions between unrelated random walks with regressions between…
This article extends a MetaTrader pending-request framework so it can place pending orders after specified activation conditions are met. A request stores its conditions and order settings; a timer checks requests and sends the order when every condition is…
The article outlines a proposed foreign-exchange triangular arbitrage system that combines three currency pairs with neural-network forecasts. It describes the basic conversion cycle and the idea of comparing implied exchange rates, then presents a workflow…
The article connects monoid actions, which let operations transform values in a separate set, to a machine-learning system that forecasts changes in price-bar range for adjusting trailing stops. It discusses feature-importance methods, including tree-based…
The article describes a modular MQL5 component for drawing Sydney, Tokyo, London, and New York trading sessions on price charts. It treats each session as an OHLC period and renders session ranges as candlestick-like shapes, with optional wicks, labels, and…
This article teaches the Money Flow Index (MFI) and offers several basic ways to turn it into systematic signals. MFI combines typical price and volume to estimate buying and selling pressure, with a calculation based on positive and negative money flow over…
This educational article explains the Money Flow Index (MFI), a volume-based oscillator that combines price and volume to estimate buying and selling pressure. It outlines the manual calculation: derive typical price, multiply by volume for raw money flow,…
This article describes updates to an MQL5 trading assistant that separates user interface components into a reusable include module and adds automated signal handling. The proposed flow checks for signals on new bars or by user request, parses AI responses…
This article introduces deep Q-learning as a reinforcement learning method that uses a neural network to estimate action values from an environment’s states. It explains that the agent learns from state, action, reward, and next-state transitions, and…
This article explains Atmosphere Clouds Model Optimization, a population-based metaheuristic inspired by cloud formation and movement. It maps a multidimensional search space into regions, each with humidity and pressure values. Clouds are created in…
This article explains Atmosphere Clouds Model Optimization, a population-based metaheuristic inspired by cloud formation and movement. It maps a multidimensional search space into regions, each with humidity and pressure values. Clouds are created in…
This article develops a way to estimate per-trade risk for a target balance and trading horizon. It first uses a fixed-fraction compounding model to relate win rate, reward-to-risk ratio, number of trades, and target growth. It then describes Monte Carlo…